当前期刊: arXiv - CS - Machine Learning Go to current issue    加入关注   
显示样式:        排序: IF: - GO 导出
我的关注
我的收藏
您暂时未登录!
登录
  • Asynchronous Distributed Optimization with Randomized Delays
    arXiv.cs.LG Pub Date : 2020-09-22
    Margalit Glasgow; Mary Wootters

    In this work, we study asynchronous finite sum minimization in a distributed-data setting with a central parameter server. While asynchrony is well understood in parallel settings where the data is accessible by all machines, little is known for the distributed-data setting. We introduce a variant of SAGA called ADSAGA for the distributed-data setting where each machine stores a partition of the data

    更新日期:2020-09-23
  • Towards a Mathematical Understanding of Neural Network-Based Machine Learning: what we know and what we don't
    arXiv.cs.LG Pub Date : 2020-09-22
    Weinan E; Chao Ma; Stephan Wojtowytsch; Lei Wu

    The purpose of this article is to review the achievements made in the last few years towards the understanding of the reasons behind the success and subtleties of neural network-based machine learning. In the tradition of good old applied mathematics, we will not only give attention to rigorous mathematical results, but also the insight we have gained from careful numerical experiments as well as the

    更新日期:2020-09-23
  • Deep Neural Tangent Kernel and Laplace Kernel Have the Same RKHS
    arXiv.cs.LG Pub Date : 2020-09-22
    Lin Chen; Sheng Xu

    We prove that the reproducing kernel Hilbert spaces (RKHS) of a deep neural tangent kernel and the Laplace kernel include the same set of functions, when both kernels are restricted to the sphere $\mathbb{S}^{d-1}$. Additionally, we prove that the exponential power kernel with a smaller power (making the kernel more non-smooth) leads to a larger RKHS, when it is restricted to the sphere $\mathbb{S}^{d-1}$

    更新日期:2020-09-23
  • Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time
    arXiv.cs.LG Pub Date : 2020-09-22
    Ferran Alet; Kenji Kawaguchi; Tomas Lozano-Perez; Leslie Pack Kaelbling

    From CNNs to attention mechanisms, encoding inductive biases into neural networks has been a fruitful source of improvement in machine learning. Auxiliary losses are a general way of encoding biases in order to help networks learn better representations by adding extra terms to the loss function. However, since they are minimized on the training data, they suffer from the same generalization gap as

    更新日期:2020-09-23
  • An Exponential Factorization Machine with Percentage Error Minimization to Retail Sales Forecasting
    arXiv.cs.LG Pub Date : 2020-09-22
    Chongshou Li; Brenda Cheang; Zhixing Luo; Andrew Lim

    This paper proposes a new approach to sales forecasting for new products with long lead time but short product life cycle. These SKUs are usually sold for one season only, without any replenishments. An exponential factorization machine (EFM) sales forecast model is developed to solve this problem which not only considers SKU attributes, but also pairwise interactions. The EFM model is significantly

    更新日期:2020-09-23
  • Property-Directed Verification of Recurrent Neural Networks
    arXiv.cs.LG Pub Date : 2020-09-22
    Igor Khmelnitsky; Daniel Neider; Rajarshi Roy; Benoît Barbot; Benedikt Bollig; Alain Finkel; Serge Haddad; Martin Leucker; Lina Ye

    This paper presents a property-directed approach to verifying recurrent neural networks (RNNs). To this end, we learn a deterministic finite automaton as a surrogate model from a given RNN using active automata learning. This model may then be analyzed using model checking as verification technique. The term property-directed reflects the idea that our procedure is guided and controlled by the given

    更新日期:2020-09-23
  • Automating Outlier Detection via Meta-Learning
    arXiv.cs.LG Pub Date : 2020-09-22
    Yue Zhao; Ryan A. Rossi; Leman Akoglu

    Given an unsupervised outlier detection (OD) task on a new dataset, how can we automatically select a good outlier detection method and its hyperparameter(s) (collectively called a model)? Thus far, model selection for OD has been a "black art"; as any model evaluation is infeasible due to the lack of (i) hold-out data with labels, and (ii) a universal objective function. In this work, we develop the

    更新日期:2020-09-23
  • Anomalous diffusion dynamics of learning in deep neural networks
    arXiv.cs.LG Pub Date : 2020-09-22
    Guozhang Chen; Cheng Kevin Qu; Pulin Gong

    Learning in deep neural networks (DNNs) is implemented through minimizing a highly non-convex loss function, typically by a stochastic gradient descent (SGD) method. This learning process can effectively find good wide minima without being trapped in poor local ones. We present a novel account of how such effective deep learning emerges through the interactions of the SGD and the geometrical structure

    更新日期:2020-09-23
  • A Centralised Soft Actor Critic Deep Reinforcement Learning Approach to District Demand Side Management through CityLearn
    arXiv.cs.LG Pub Date : 2020-09-22
    Anjukan Kathirgamanathan; Kacper Twardowski; Eleni Mangina; Donal Finn

    Reinforcement learning is a promising model-free and adaptive controller for demand side management, as part of the future smart grid, at the district level. This paper presents the results of the algorithm that was submitted for the CityLearn Challenge, which was hosted in early 2020 with the aim of designing and tuning a reinforcement learning agent to flatten and smooth the aggregated curve of electrical

    更新日期:2020-09-23
  • Local Post-Hoc Explanations for Predictive Process Monitoring in Manufacturing
    arXiv.cs.LG Pub Date : 2020-09-22
    Nijat Mehdiyev; Peter Fettke

    This study proposes an innovative explainable process prediction solution to facilitate the data-driven decision making for process planning in manufacturing. After integrating the top-floor and shop-floor data obtained from various enterprise information systems especially from Manufacturing Execution Systems, a deep neural network was applied to predict the process outcomes. Since we aim to operationalize

    更新日期:2020-09-23
  • Adversarial Training with Stochastic Weight Average
    arXiv.cs.LG Pub Date : 2020-09-21
    Joong-Won Hwang; Youngwan Lee; Sungchan Oh; Yuseok Bae

    Adversarial training deep neural networks often experience serious overfitting problem. Recently, it is explained that the overfitting happens because the sample complexity of training data is insufficient to generalize robustness. In traditional machine learning, one way to relieve overfitting from the lack of data is to use ensemble methods. However, adversarial training multiple networks is extremely

    更新日期:2020-09-23
  • Privacy Preserving K-Means Clustering: A Secure Multi-Party Computation Approach
    arXiv.cs.LG Pub Date : 2020-09-22
    Daniel Hurtado Ramírez; J. M. Auñón

    Knowledge discovery is one of the main goals of Artificial Intelligence. This Knowledge is usually stored in databases spread in different environments, being a tedious (or impossible) task to access and extract data from them. To this difficulty we must add that these datasources may contain private data, therefore the information can never leave the source. Privacy Preserving Machine Learning (PPML)

    更新日期:2020-09-23
  • Is Q-Learning Provably Efficient? An Extended Analysis
    arXiv.cs.LG Pub Date : 2020-09-22
    Kushagra Rastogi; Jonathan Lee; Fabrice Harel-Canada; Aditya Joglekar

    This work extends the analysis of the theoretical results presented within the paper Is Q-Learning Provably Efficient? by Jin et al. We include a survey of related research to contextualize the need for strengthening the theoretical guarantees related to perhaps the most important threads of model-free reinforcement learning. We also expound upon the reasoning used in the proofs to highlight the critical

    更新日期:2020-09-23
  • PS8-Net: A Deep Convolutional Neural Network to Predict the Eight-State Protein Secondary Structure
    arXiv.cs.LG Pub Date : 2020-09-22
    Md Aminur Rab Ratul; Maryam Tavakol Elahi; M. Hamed Mozaffari; WonSook Lee

    Protein secondary structure is crucial to creating an information bridge between the primary and tertiary (3D) structures. Precise prediction of eight-state protein secondary structure (PSS) has significantly utilized in the structural and functional analysis of proteins in bioinformatics. Deep learning techniques have been recently applied in this research area and raised the eight-state (Q8) protein

    更新日期:2020-09-23
  • Explainable, Stable, and Scalable Graph Convolutional Networks for Learning Graph Representation
    arXiv.cs.LG Pub Date : 2020-09-22
    Ping-En Lu; Cheng-Shang Chang

    The network embedding problem that maps nodes in a graph to vectors in Euclidean space can be very useful for addressing several important tasks on a graph. Recently, graph neural networks (GNNs) have been proposed for solving such a problem. However, most embedding algorithms and GNNs are difficult to interpret and do not scale well to handle millions of nodes. In this paper, we tackle the problem

    更新日期:2020-09-23
  • Inter-database validation of a deep learning approach for automatic sleep scoring
    arXiv.cs.LG Pub Date : 2020-09-22
    Diego Alvarez-Estevez; Roselyne M. Rijsman

    In this work we describe a new deep learning approach for automatic sleep staging, and carry out its validation by addressing its generalization capabilities on a wide range of sleep staging databases. Prediction capabilities are evaluated in the context of independent local and external generalization scenarios. Effectively, by comparing both procedures it is possible to better extrapolate the expected

    更新日期:2020-09-23
  • Gamma distribution-based sampling for imbalanced data
    arXiv.cs.LG Pub Date : 2020-09-22
    Firuz Kamalov; Dmitry Denisov

    Imbalanced class distribution is a common problem in a number of fields including medical diagnostics, fraud detection, and others. It causes bias in classification algorithms leading to poor performance on the minority class data. In this paper, we propose a novel method for balancing the class distribution in data through intelligent resampling of the minority class instances. The proposed method

    更新日期:2020-09-23
  • Learning Task-Agnostic Action Spaces for Movement Optimization
    arXiv.cs.LG Pub Date : 2020-09-22
    Amin Babadi; Michiel van de Panne; C. Karen Liu; Perttu Hämäläinen

    We propose a novel method for exploring the dynamics of physically based animated characters, and learning a task-agnostic action space that makes movement optimization easier. Like several previous papers, we parameterize actions as target states, and learn a short-horizon goal-conditioned low-level control policy that drives the agent's state towards the targets. Our novel contribution is that with

    更新日期:2020-09-23
  • DeepVir -- Graphical Deep Matrix Factorization for "In Silico" Antiviral Repositioning: Application to COVID-19
    arXiv.cs.LG Pub Date : 2020-09-22
    Aanchal Mongia; Stuti Jain; Emilie Chouzenoux; Angshul Majumda

    This work formulates antiviral repositioning as a matrix completion problem where the antiviral drugs are along the rows and the viruses along the columns. The input matrix is partially filled, with ones in positions where the antiviral has been known to be effective against a virus. The curated metadata for antivirals (chemical structure and pathways) and viruses (genomic structure and symptoms) is

    更新日期:2020-09-23
  • Public Health Informatics: Proposing Causal Sequence of Death Using Neural Machine Translation
    arXiv.cs.LG Pub Date : 2020-09-22
    Yuanda Zhu; Ying Sha; Hang Wu; Mai Li; Ryan A. Hoffman; May D. Wang

    Each year there are nearly 57 million deaths around the world, with over 2.7 million in the United States. Timely, accurate and complete death reporting is critical in public health, as institutions and government agencies rely on death reports to analyze vital statistics and to formulate responses to communicable diseases. Inaccurate death reporting may result in potential misdirection of public health

    更新日期:2020-09-23
  • Stacked Generalization for Human Activity Recognition
    arXiv.cs.LG Pub Date : 2020-09-22
    Ambareesh Ravi

    This short paper aims to discuss the effectiveness and performance of classical machine learning approaches for Human Activity Recognition (HAR). It proposes two important models - Extra Trees and Stacked Classifier with the emphasize on the best practices, heuristics and measures that are required to maximize the performance of those models.

    更新日期:2020-09-23
  • Sub-graph Contrast for Scalable Self-Supervised Graph Representation Learning
    arXiv.cs.LG Pub Date : 2020-09-22
    Yizhu Jiao; Yun Xiong; Jiawei Zhang; Yao Zhang; Tianqi Zhang; Yangyong Zhu

    Graph representation learning has attracted lots of attention recently. Existing graph neural networks fed with the complete graph data are not scalable due to limited computation and memory costs. Thus, it remains a great challenge to capture rich information in large-scale graph data. Besides, these methods mainly focus on supervised learning and highly depend on node label information, which is

    更新日期:2020-09-23
  • An Incentive Mechanism for Federated Learning in Wireless Cellular network: An Auction Approach
    arXiv.cs.LG Pub Date : 2020-09-22
    Tra Huong Thi Le; Nguyen H. Tran; Yan Kyaw Tun; Minh N. H. Nguyen; Shashi Raj Pandey; Zhu Han; Choong Seon Hong

    Federated Learning (FL) is a distributed learning framework that can deal with the distributed issue in machine learning and still guarantee high learning performance. However, it is impractical that all users will sacrifice their resources to join the FL algorithm. This motivates us to study the incentive mechanism design for FL. In this paper, we consider a FL system that involves one base station

    更新日期:2020-09-23
  • Semantic Workflows and Machine Learning for the Assessment of Carbon Storage by Urban Trees
    arXiv.cs.LG Pub Date : 2020-09-22
    Juan Carrillo; Daniel Garijo; Mark Crowley; Rober Carrillo; Yolanda Gil; Katherine Borda

    Climate science is critical for understanding both the causes and consequences of changes in global temperatures and has become imperative for decisive policy-making. However, climate science studies commonly require addressing complex interoperability issues between data, software, and experimental approaches from multiple fields. Scientific workflow systems provide unparalleled advantages to address

    更新日期:2020-09-23
  • Uncertainty-aware Attention Graph Neural Network for Defending Adversarial Attacks
    arXiv.cs.LG Pub Date : 2020-09-22
    Boyuan Feng; Yuke Wang; Zheng Wang; Yufei Ding

    With the increasing popularity of graph-based learning, graph neural networks (GNNs) emerge as the essential tool for gaining insights from graphs. However, unlike the conventional CNNs that have been extensively explored and exhaustively tested, people are still worrying about the GNNs' robustness under the critical settings, such as financial services. The main reason is that existing GNNs usually

    更新日期:2020-09-23
  • Scalable Adversarial Attack on Graph Neural Networks with Alternating Direction Method of Multipliers
    arXiv.cs.LG Pub Date : 2020-09-22
    Boyuan Feng; Yuke Wang; Xu Li; Yufei Ding

    Graph neural networks (GNNs) have achieved high performance in analyzing graph-structured data and have been widely deployed in safety-critical areas, such as finance and autonomous driving. However, only a few works have explored GNNs' robustness to adversarial attacks, and their designs are usually limited by the scale of input datasets (i.e., focusing on small graphs with only thousands of nodes)

    更新日期:2020-09-23
  • Survey of explainable machine learning with visual and granular methods beyond quasi-explanations
    arXiv.cs.LG Pub Date : 2020-09-21
    Boris KovalerchukDepartment of Computer Science, Central Washington University, USA; Muhammad Aurangzeb AhmadDepartment of Computer Science and Systems, University of Washington Tacoma, USAKensci Inc., USA; Ankur TeredesaiDepartment of Computer Science and Systems, University of Washington Tacoma, USAKensci Inc., USA

    This paper surveys visual methods of explainability of Machine Learning (ML) with focus on moving from quasi-explanations that dominate in ML to domain-specific explanation supported by granular visuals. ML interpretation is fundamentally a human activity and visual methods are more readily interpretable. While efficient visual representations of high-dimensional data exist, the loss of interpretable

    更新日期:2020-09-23
  • DISPATCH: Design Space Exploration of Cyber-Physical Systems
    arXiv.cs.LG Pub Date : 2020-09-21
    Prerit Terway; Kenza Hamidouche; Niraj K. Jha

    Design of Cyber-physical systems (CPSs) is a challenging task that involves searching over a large search space of various CPS configurations and possible values of components composing the system. Hence, there is a need for sample-efficient CPS design space exploration to select the system architecture and component values that meet the target system requirements. We address this challenge by formulating

    更新日期:2020-09-23
  • Resilient In-Season Crop Type Classification in Multispectral Satellite Observations using Growth Stage Normalization
    arXiv.cs.LG Pub Date : 2020-09-21
    Hannah Kerner; Ritvik Sahajpal; Sergii Skakun; Inbal Becker-Reshef; Brian Barker; Mehdi Hosseini; Estefania Puricelli; Patrick Gray

    Crop type classification using satellite observations is an important tool for providing insights about planted area and enabling estimates of crop condition and yield, especially within the growing season when uncertainties around these quantities are highest. As the climate changes and extreme weather events become more frequent, these methods must be resilient to changes in domain shifts that may

    更新日期:2020-09-23
  • Crafting Adversarial Examples for Deep Learning Based Prognostics (Extended Version)
    arXiv.cs.LG Pub Date : 2020-09-21
    Gautam Raj Mode; Khaza Anuarul Hoque

    In manufacturing, unexpected failures are considered a primary operational risk, as they can hinder productivity and can incur huge losses. State-of-the-art Prognostics and Health Management (PHM) systems incorporate Deep Learning (DL) algorithms and Internet of Things (IoT) devices to ascertain the health status of equipment, and thus reduce the downtime, maintenance cost and increase the productivity

    更新日期:2020-09-23
  • Bandits Under The Influence (Extended Version)
    arXiv.cs.LG Pub Date : 2020-09-21
    Silviu Maniu; Stratis Ioannidis; Bogdan Cautis

    Recommender systems should adapt to user interests as the latter evolve. A prevalent cause for the evolution of user interests is the influence of their social circle. In general, when the interests are not known, online algorithms that explore the recommendation space while also exploiting observed preferences are preferable. We present online recommendation algorithms rooted in the linear multi-armed

    更新日期:2020-09-23
  • TSV Extrusion Morphology Classification Using Deep Convolutional Neural Networks
    arXiv.cs.LG Pub Date : 2020-09-22
    Brendan Reidy; Golareh Jalilvand; Tengfei Jiang; Ramtin Zand

    In this paper, we utilize deep convolutional neural networks (CNNs) to classify the morphology of through-silicon via (TSV) extrusion in three dimensional (3D) integrated circuits (ICs). TSV extrusion is a crucial reliability concern which can deform and crack interconnect layers in 3D ICs and cause device failures. Herein, the white light interferometry (WLI) technique is used to obtain the surface

    更新日期:2020-09-23
  • Contextual Bandits for adapting to changing User preferences over time
    arXiv.cs.LG Pub Date : 2020-09-21
    Dattaraj Rao

    Contextual bandits provide an effective way to model this problem and leverage online (incremental) learning to keep adjusting the predictions based on changing environment. We explore how contextual bandits problem is modelled as an extension of the reinforcement learning (RL) problem and build a novel algorithm to solve the problem using an array of action-based learners. We apply this approach to

    更新日期:2020-09-23
  • Let's Stop Incorrect Comparisons in End-to-end Relation Extraction!
    arXiv.cs.LG Pub Date : 2020-09-22
    Bruno Taillé; Vincent Guigue; Geoffrey Scoutheeten; Patrick Gallinari

    Despite efforts to distinguish three different evaluation setups (Bekoulis et al., 2018), numerous end-to-end Relation Extraction (RE) articles present unreliable performance comparison to previous work. In this paper, we first identify several patterns of invalid comparisons in published papers and describe them to avoid their propagation. We then propose a small empirical study to quantify the impact

    更新日期:2020-09-23
  • Ultra-dense Low Data Rate (UDLD) Communication in the THz
    arXiv.cs.LG Pub Date : 2020-09-22
    Rohit Singh; Doug Sicker

    In the future, with the advent of Internet of Things (IoT), wireless sensors, and multiple 5G killer applications, an indoor room might be filled with $1000$s of devices demanding low data rates. Such high-level densification and mobility of these devices will overwhelm the system and result in higher interference, frequent outages, and lower coverage. The THz band has a massive amount of greenfield

    更新日期:2020-09-23
  • On the proliferation of support vectors in high dimensions
    arXiv.cs.LG Pub Date : 2020-09-22
    Daniel Hsu; Vidya Muthukumar; Ji Xu

    The support vector machine (SVM) is a well-established classification method whose name refers to the particular training examples, called support vectors, that determine the maximum margin separating hyperplane. The SVM classifier is known to enjoy good generalization properties when the number of support vectors is small compared to the number of training examples. However, recent research has shown

    更新日期:2020-09-23
  • E-BATCH: Energy-Efficient and High-Throughput RNN Batching
    arXiv.cs.LG Pub Date : 2020-09-22
    Franyell Silfa; Jose Maria Arnau; Antonio Gonzalez

    Recurrent Neural Network (RNN) inference exhibits low hardware utilization due to the strict data dependencies across time-steps. Batching multiple requests can increase throughput. However, RNN batching requires a large amount of padding since the batched input sequences may largely differ in length. Schemes that dynamically update the batch every few time-steps avoid padding. However, they require

    更新日期:2020-09-23
  • Partially Observable Online Change Detection via Smooth-Sparse Decomposition
    arXiv.cs.LG Pub Date : 2020-09-22
    Jie Guo; Hao Yan; Chen Zhang; Steven Hoi

    We consider online change detection of high dimensional data streams with sparse changes, where only a subset of data streams can be observed at each sensing time point due to limited sensing capacities. On the one hand, the detection scheme should be able to deal with partially observable data and meanwhile have efficient detection power for sparse changes. On the other, the scheme should be able

    更新日期:2020-09-23
  • Using Neural Architecture Search for Improving Software Flaw Detection in Multimodal Deep Learning Models
    arXiv.cs.LG Pub Date : 2020-09-22
    Alexis Cooper; Xin Zhou; Scott Heidbrink; Daniel M. Dunlavy

    Software flaw detection using multimodal deep learning models has been demonstrated as a very competitive approach on benchmark problems. In this work, we demonstrate that even better performance can be achieved using neural architecture search (NAS) combined with multimodal learning models. We adapt a NAS framework aimed at investigating image classification to the problem of software flaw detection

    更新日期:2020-09-23
  • What Do You See? Evaluation of Explainable Artificial Intelligence (XAI) Interpretability through Neural Backdoors
    arXiv.cs.LG Pub Date : 2020-09-22
    Yi-Shan Lin; Wen-Chuan Lee; Z. Berkay Celik

    EXplainable AI (XAI) methods have been proposed to interpret how a deep neural network predicts inputs through model saliency explanations that highlight the parts of the inputs deemed important to arrive a decision at a specific target. However, it remains challenging to quantify correctness of their interpretability as current evaluation approaches either require subjective input from humans or incur

    更新日期:2020-09-23
  • Overlapping community detection in networks via sparse spectral decomposition
    arXiv.cs.LG Pub Date : 2020-09-20
    Jesús Arroyo; Elizaveta Levina

    We consider the problem of estimating overlapping community memberships in a network, where each node can belong to multiple communities. More than a few communities per node are difficult to both estimate and interpret, so we focus on sparse node membership vectors. Our algorithm is based on sparse principal subspace estimation with iterative thresholding. The method is computationally efficient,

    更新日期:2020-09-23
  • ThingML+ Augmenting Model-Driven Software Engineering for the Internet of Things with Machine Learning
    arXiv.cs.LG Pub Date : 2020-09-22
    Armin Moin; Stephan Rössler; Stephan Günnemann

    In this paper, we present the current position of the research project ML-Quadrat, which aims to extend the methodology, modeling language and tool support of ThingML - an open source modeling tool for IoT/CPS - to address Machine Learning needs for the IoT applications. Currently, ThingML offers a modeling language and tool support for modeling the components of the system, their communication interfaces

    更新日期:2020-09-23
  • From Things' Modeling Language (ThingML) to Things' Machine Learning (ThingML2)
    arXiv.cs.LG Pub Date : 2020-09-22
    Armin Moin; Stephan Rössler; Marouane Sayih; Stephan Günnemann

    In this paper, we illustrate how to enhance an existing state-of-the-art modeling language and tool for the Internet of Things (IoT), called ThingML, to support machine learning on the modeling level. To this aim, we extend the Domain-Specific Language (DSL) of ThingML, as well as its code generation framework. Our DSL allows one to define things, which are in charge of carrying out data analytics

    更新日期:2020-09-23
  • Forecasting elections results via the voter model with stubborn nodes
    arXiv.cs.LG Pub Date : 2020-09-22
    Antoine Vendeville; Benjamin Guedj; Shi Zhou

    In this paper we propose a novel method to forecast the result of elections using only official results of previous ones. It is based on the voter model with stubborn nodes and uses theoretical results developed in a previous work of ours. We look at popular vote shares for the Conservative and Labour parties in the UK and the Republican and Democrat parties in the US. We are able to perform time-evolving

    更新日期:2020-09-23
  • Curriculum Learning with Diversity for Supervised Computer Vision Tasks
    arXiv.cs.LG Pub Date : 2020-09-22
    Petru Soviany

    Curriculum learning techniques are a viable solution for improving the accuracy of automatic models, by replacing the traditional random training with an easy-to-hard strategy. However, the standard curriculum methodology does not automatically provide improved results, but it is constrained by multiple elements like the data distribution or the proposed model. In this paper, we introduce a novel curriculum

    更新日期:2020-09-23
  • Ethical Machine Learning in Health
    arXiv.cs.LG Pub Date : 2020-09-22
    Irene Y. Chen; Emma Pierson; Sherri Rose; Shalmali Joshi; Kadija Ferryman; Marzyeh Ghassemi

    The use of machine learning (ML) in health care raises numerous ethical concerns, especially as models can amplify existing health inequities. Here, we outline ethical considerations for equitable ML in the advancement of health care. Specifically, we frame ethics of ML in health care through the lens of social justice. We describe ongoing efforts and outline challenges in a proposed pipeline of ethical

    更新日期:2020-09-23
  • A Survey and Taxonomy of Distributed Data Mining Research Studies: A Systematic Literature Review
    arXiv.cs.LG Pub Date : 2020-09-14
    Fauzi Adi Rafrastara; Qi Deyu

    Context: Data Mining (DM) method has been evolving year by year and as of today there is also the enhancement of DM technique that can be run several times faster than the traditional one, called Distributed Data Mining (DDM). It is not a new field in data processing actually, but in the recent years many researchers have been paying more attention on this area. Problems: The number of publication

    更新日期:2020-09-23
  • Mosques Smart Domes System using Machine Learning Algorithms
    arXiv.cs.LG Pub Date : 2020-08-30
    Mohammad Awis Al Lababede; Anas H. Blasi; Mohammed A. Alsuwaiket

    Millions of mosques around the world are suffering some problems such as ventilation and difficulty getting rid of bacteria, especially in rush hours where congestion in mosques leads to air pollution and spread of bacteria, in addition to unpleasant odors and to a state of discomfort during the pray times, where in most mosques there are no enough windows to ventilate the mosque well. This paper aims

    更新日期:2020-09-23
  • Learning Concepts Described by Weight Aggregation Logic
    arXiv.cs.LG Pub Date : 2020-09-22
    Steffen van Bergerem; Nicole Schweikardt

    We consider weighted structures, which extend ordinary relational structures by assigning weights, i.e. elements from a particular group or ring, to tuples present in the structure. We introduce an extension of first-order logic that allows to aggregate weights of tuples, compare such aggregates, and use them to build more complex formulas. We provide locality properties of fragments of this logic

    更新日期:2020-09-23
  • EI-MTD:Moving Target Defense for Edge Intelligence against Adversarial Attacks
    arXiv.cs.LG Pub Date : 2020-09-19
    Yaguan Qian; Qiqi Shao; Jiamin Wang; Xiang Lin; Yankai Guo; Zhaoquan Gu; Bin Wang; Chunming Wu

    With the boom of edge intelligence, its vulnerability to adversarial attacks becomes an urgent problem. The so-called adversarial example can fool a deep learning model on the edge node to misclassify. Due to the property of transferability, the adversary can easily make a black-box attack using a local substitute model. Nevertheless, the limitation of resource of edge nodes cannot afford a complicated

    更新日期:2020-09-23
  • Early detection of the advanced persistent threat attack using performance analysis of deep learning
    arXiv.cs.LG Pub Date : 2020-09-19
    Javad Hassannataj Joloudari; Mojtaba Haderbadi; Amir Mashmool; Mohammad GhasemiGol; Shahab S.; Amir Mosavi

    One of the most common and important destructive attacks on the victim system is Advanced Persistent Threat (APT)-attack. The APT attacker can achieve his hostile goals by obtaining information and gaining financial benefits regarding the infrastructure of a network. One of the solutions to detect a secret APT attack is using network traffic. Due to the nature of the APT attack in terms of being on

    更新日期:2020-09-23
  • Self-Supervised Learning of Non-Rigid Residual Flow and Ego-Motion
    arXiv.cs.LG Pub Date : 2020-09-22
    Ivan Tishchenko; Sandro Lombardi; Martin R. Oswald; Marc Pollefeys

    Most of the current scene flow methods choose to model scene flow as a per point translation vector without differentiating between static and dynamic components of 3D motion. In this work we present an alternative method for end-to-end scene flow learning by joint estimation of non-rigid residual flow and ego-motion flow for dynamic 3D scenes. We propose to learn the relative rigid transformation

    更新日期:2020-09-23
  • Integration of Clinical Criteria into the Training of Deep Models: Application to Glucose Prediction for Diabetic People
    arXiv.cs.LG Pub Date : 2020-09-21
    Maxime De Bois; Mounîm A. El Yacoubi

    Standard objective functions used during the training of neural-network-based predictive models do not consider clinical criteria, leading to models that are not necessarily clinically acceptable. In this study, we look at this problem from the perspective of the forecasting of future glucose values for diabetic people. In this study, we propose the coherent mean squared glycemic error (gcMSE) loss

    更新日期:2020-09-23
  • Dynamic Fusion based Federated Learning for COVID-19 Detection
    arXiv.cs.LG Pub Date : 2020-09-22
    Weishan Zhang; Tao Zhou; Qinghua Lu; Xiao Wang; Chunsheng Zhu; Zhipeng Wang; Feiyue Wang

    Medical diagnostic image analysis (e.g., CT scan or X-Ray) using machine learning is expected to be an efficient and accurate way to detect COVID-19 infections. However, sharing diagnostic images across medical institutions is usually not allowed due to the concern of patients' privacy, which causes the issue of insufficient datasets for training the image classification model. Federated learning is

    更新日期:2020-09-23
  • Mixed-Projection Conic Optimization: A New Paradigm for Modeling Rank Constraints
    arXiv.cs.LG Pub Date : 2020-09-22
    Dimitris Bertsimas; Ryan Cory-Wright; Jean Pauphilet

    We propose a framework for modeling and solving low-rank optimization problems to certifiable optimality. We introduce symmetric projection matrices that satisfy $Y^2=Y$, the matrix analog of binary variables that satisfy $z^2=z$, to model rank constraints. By leveraging regularization and strong duality, we prove that this modeling paradigm yields tractable convex optimization problems over the non-convex

    更新日期:2020-09-23
  • PodSumm -- Podcast Audio Summarization
    arXiv.cs.LG Pub Date : 2020-09-22
    Aneesh Vartakavi; Amanmeet Garg

    The diverse nature, scale, and specificity of podcasts present a unique challenge to content discovery systems. Listeners often rely on text descriptions of episodes provided by the podcast creators to discover new content. Some factors like the presentation style of the narrator and production quality are significant indicators of subjective user preference but are difficult to quantify and not reflected

    更新日期:2020-09-23
  • An adaptive transport framework for joint and conditional density estimation
    arXiv.cs.LG Pub Date : 2020-09-22
    Ricardo Baptista; Olivier Zahm; Youssef Marzouk

    We propose a general framework to robustly characterize joint and conditional probability distributions via transport maps. Transport maps or "flows" deterministically couple two distributions via an expressive monotone transformation. Yet, learning the parameters of such transformations in high dimensions is challenging given few samples from the unknown target distribution, and structural choices

    更新日期:2020-09-23
  • Stochastic Neighbor Embedding with Gaussian and Student-t Distributions: Tutorial and Survey
    arXiv.cs.LG Pub Date : 2020-09-22
    Benyamin Ghojogh; Ali Ghodsi; Fakhri Karray; Mark Crowley

    Stochastic Neighbor Embedding (SNE) is a manifold learning and dimensionality reduction method with a probabilistic approach. In SNE, every point is consider to be the neighbor of all other points with some probability and this probability is tried to be preserved in the embedding space. SNE considers Gaussian distribution for the probability in both the input and embedding spaces. However, t-SNE uses

    更新日期:2020-09-23
  • End-to-End Speech Recognition and Disfluency Removal
    arXiv.cs.LG Pub Date : 2020-09-22
    Paria Jamshid Lou; Mark Johnson

    Disfluency detection is usually an intermediate step between an automatic speech recognition (ASR) system and a downstream task. By contrast, this paper aims to investigate the task of end-to-end speech recognition and disfluency removal. We specifically explore whether it is possible to train an ASR model to directly map disfluent speech into fluent transcripts, without relying on a separate disfluency

    更新日期:2020-09-23
  • End-to-End Learning of Speech 2D Feature-Trajectory for Prosthetic Hands
    arXiv.cs.LG Pub Date : 2020-09-22
    Mohsen Jafarzadeh; Yonas Tadesse

    Speech is one of the most common forms of communication in humans. Speech commands are essential parts of multimodal controlling of prosthetic hands. In the past decades, researchers used automatic speech recognition systems for controlling prosthetic hands by using speech commands. Automatic speech recognition systems learn how to map human speech to text. Then, they used natural language processing

    更新日期:2020-09-23
Contents have been reproduced by permission of the publishers.
导出
全部期刊列表>>
物理学研究前沿热点精选期刊推荐
chemistry
《自然》编辑与您分享如何成为优质审稿人-信息流
欢迎报名注册2020量子在线大会
化学领域亟待解决的问题
材料学研究精选新
GIANT
自然职场线上招聘会
ACS ES&T Engineering
ACS ES&T Water
ACS Publications填问卷
屿渡论文,编辑服务
阿拉丁试剂right
南昌大学
王辉
南方科技大学
刘天飞
隐藏1h前已浏览文章
课题组网站
新版X-MOL期刊搜索和高级搜索功能介绍
ACS材料视界
天合科研
x-mol收录
X-MOL
苏州大学
廖矿标
深圳湾
试剂库存
down
wechat
bug